# Button1 on Safety Gymnasium

Source: [Button1 on Safety Gymnasium](<https://www.sota2.com/research/sota/button1-on-safety-gymnasium>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:02:18.361Z

Evaluation of performance on the Button1 task within the Safety Gymnasium environment, measured by Reward and Cost.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Button1 |
| Dataset (including any stated split) | Safety Gymnasium |
| Metric | Reward |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Reward](<https://www.sota2.com/research/sota/button1-on-safety-gymnasium.md?metric=Reward>): Higher is better; unit: SCALAR.

- [Cost](<https://www.sota2.com/research/sota/button1-on-safety-gymnasium.md?metric=Cost>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Reward | Result date | Report paper |
| --- | --- | --- | --- |
| USC (NR) | 7.65 | Not recorded | 68fa7c6b1e209131cea8df7e |
| USC | 6.41 | Not recorded | 68fa7c6b1e209131cea8df7e |
| USC | 6.38 | Not recorded | 68fa7c6b1e209131cea8df7e |
| USC (NR) | 6.31 | Not recorded | 68fa7c6b1e209131cea8df7e |
| CPO | 6.22 | Not recorded | 68fa7c6b1e209131cea8df7e |
| DDPG | 6.2 | Not recorded | 68fa7c6b1e209131cea8df7e |
| CPO | 5.99 | Not recorded | 68fa7c6b1e209131cea8df7e |
| CSC | 5.48 | Not recorded | 68fa7c6b1e209131cea8df7e |
| DDPG | 5.36 | Not recorded | 68fa7c6b1e209131cea8df7e |
| SC | 5.12 | Not recorded | 68fa7c6b1e209131cea8df7e |
| RCPO | 4.21 | Not recorded | 68fa7c6b1e209131cea8df7e |
| CSC | 3.96 | Not recorded | 68fa7c6b1e209131cea8df7e |
| SC | 2.63 | Not recorded | 68fa7c6b1e209131cea8df7e |
| PID-Lag | 2.49 | Not recorded | 68fa7c6b1e209131cea8df7e |
| PID-Lag | 0.07 | Not recorded | 68fa7c6b1e209131cea8df7e |
| RCPO | -0.01 | Not recorded | 68fa7c6b1e209131cea8df7e |

### USC (NR)

Reward: 7.65. Result ID: 699af4305698665ec4857bb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

Recorded evaluation configuration: {"chi":"5.0","Refinement":"None"}. This record does not assert independent reproduction.

### USC

Reward: 6.41. Result ID: 699af4305698665ec4857bba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

Recorded evaluation configuration: {"chi":"5.0","Refinement":"Refined"}. This record does not assert independent reproduction.

### USC

Reward: 6.38. Result ID: 699af4305698665ec4857c12.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"5.0"}. This record does not assert independent reproduction.

### USC (NR)

Reward: 6.31. Result ID: 699af4305698665ec4857c11.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"5.0"}. This record does not assert independent reproduction.

### CPO

Reward: 6.22. Result ID: 699af4305698665ec4857bb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63691e209131ce9fe8ff.md>)

Recorded evaluation configuration: {"chi":"5.0"}. This record does not assert independent reproduction.

### DDPG

Reward: 6.2. Result ID: 699af4305698665ec4857c0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fd1e209131cea0dc8e.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"5.0"}. This record does not assert independent reproduction.

### CPO

Reward: 5.99. Result ID: 699af4305698665ec4857c0d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63691e209131ce9fe8ff.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"5.0"}. This record does not assert independent reproduction.

### CSC

Reward: 5.48. Result ID: 699af4305698665ec4857c10.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea2424d.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"5.0"}. This record does not assert independent reproduction.

### DDPG

Reward: 5.36. Result ID: 699af4305698665ec4857bb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65fd1e209131cea0dc8e.md>)

Recorded evaluation configuration: {"chi":"5.0"}. This record does not assert independent reproduction.

### SC

Reward: 5.12. Result ID: 699af4305698665ec4857c0f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa689d1e209131cea1d196.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"5.0"}. This record does not assert independent reproduction.

### RCPO

Reward: 4.21. Result ID: 699af4305698665ec4857c0e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65321e209131cea08cff.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"5.0"}. This record does not assert independent reproduction.

### CSC

Reward: 3.96. Result ID: 699af4305698665ec4857bb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea2424d.md>)

Recorded evaluation configuration: {"chi":"5.0"}. This record does not assert independent reproduction.

### SC

Reward: 2.63. Result ID: 699af4305698665ec4857bb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa689d1e209131cea1d196.md>)

Recorded evaluation configuration: {"chi":"5.0"}. This record does not assert independent reproduction.

### PID-Lag

Reward: 2.49. Result ID: 699af4305698665ec4857c0c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa571c1e209131ce9a29c4.md>)

Recorded evaluation configuration: {"Cost Limit (chi)":"5.0"}. This record does not assert independent reproduction.

### PID-Lag

Reward: 0.07. Result ID: 699af4305698665ec4857bb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa571c1e209131ce9a29c4.md>)

Recorded evaluation configuration: {"chi":"5.0"}. This record does not assert independent reproduction.

### RCPO

Reward: -0.01. Result ID: 699af4305698665ec4857bb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c6b1e209131cea8df7e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65321e209131cea08cff.md>)

Recorded evaluation configuration: {"chi":"5.0"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
